library(tidyverse)
library(forcats)
library(cowplot)
##
## Attaching package: 'cowplot'
## The following object is masked _by_ '.GlobalEnv':
##
## save_plot
## The following object is masked from 'package:lubridate':
##
## stamp
library(ggupset)
library(RColorBrewer)
library(patchwork)
##
## Attaching package: 'patchwork'
## The following object is masked from 'package:cowplot':
##
## align_plots
library(vegan)
## Loading required package: permute
## Loading required package: lattice
## This is vegan 2.6-4
library(pheatmap)
library(broom)
data <- targets::tar_read(merged_all_results)
# rename BLAST to BLAST97 to differentiate from BLAST100 (percentage identity in both cases)
data <- data |> mutate(Type = str_replace(Type, '^BLAST$', 'BLAST97'))
truth <- targets::tar_read(truth_set_data)
table(data$Type)
##
## BLAST100 BLAST97 Kraken_0.0 Kraken_0.1 Kraken_0.2 Kraken_0.3 Kraken_0.4
## 18050 27786 110080 110080 110080 55040 55040
## Kraken_0.5 Kraken_0.6 Kraken_0.7 Kraken_0.8 Kraken_0.9 Metabuli MMSeqs2
## 55040 55040 55040 55040 55040 65090 179712
## Mothur NBC Qiime2 VSEARCH
## 174096 196560 53150 26662
Let’s remove the >0.2 Kraken runs, those are too strict
data <- data |> filter(!Type %in% c('Kraken_0.3', 'Kraken_0.4', 'Kraken_0.5', 'Kraken_0.6', 'Kraken_0.7', 'Kraken_0.8', 'Kraken_0.9'))
Made a mistake- Metabuli’s Database is misspelled
data <- data |> mutate(Subject = str_replace_all(Subject, pattern = '_ref.fasta', replacement=''))
data |> write_tsv('./data/cleaned_and_filtered_data.tsv.gz')
table(data$Query)
##
## KWest_16S_PooledTrue.fa
## 274310
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa
## 98290
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_noLulu_RESULTS_dada2_asv.fa
## 98290
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_Lulu_RESULTS_dada2_asv.fa
## 93066
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_noLulu_RESULTS_dada2_asv.fa
## 93066
## make_12s_16s_simulated_reads_6-fakeGenes_GreenGenes_RESULTS_dada2_asv.fa
## 78382
## make_12s_16s_simulated_reads_6-fakeGenes_Random_RESULTS_dada2_asv.fa
## 78662
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_12S_RESULTS_dada2_asv.fa
## 24562
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_16S_RESULTS_dada2_asv.fa
## 25882
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_12S_RESULTS_dada2_asv.fa
## 101384
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_16S_RESULTS_dada2_asv.fa
## 105452
table(data$Subject)
##
## 12s_v010_final.fasta
## 16948
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_1.fasta
## 15894
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 15530
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_2.fasta
## 15780
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 15862
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_4.fasta
## 15700
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_5.fasta
## 15908
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 15324
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_7.fasta
## 15434
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_8.fasta
## 16196
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 16038
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_1.fasta
## 16468
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_10.fasta
## 16072
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 16080
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_3.fasta
## 16470
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_4.fasta
## 16154
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 16126
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_6.fasta
## 16024
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_7.fasta
## 16296
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_8.fasta
## 16062
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_9.fasta
## 16268
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_1.fasta
## 14966
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_10.fasta
## 14854
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_2.fasta
## 15352
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_3.fasta
## 15118
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_4.fasta
## 15274
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_5.fasta
## 15256
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_6.fasta
## 14744
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_7.fasta
## 15020
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_8.fasta
## 14828
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_9.fasta
## 15274
## 12S_v10_HmmCut.fasta
## 11732
## 16S_v04_final.fasta
## 19470
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_1.fasta
## 17626
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 16826
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_2.fasta
## 17332
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 17298
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_4.fasta
## 17600
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_5.fasta
## 17770
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 16762
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_7.fasta
## 17730
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_8.fasta
## 16610
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 17000
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_1.fasta
## 18248
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_10.fasta
## 18446
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 18110
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_3.fasta
## 17614
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_4.fasta
## 18126
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 18740
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_6.fasta
## 17816
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_7.fasta
## 18572
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_8.fasta
## 18464
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_9.fasta
## 18744
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_1.fasta
## 17498
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_10.fasta
## 16792
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_2.fasta
## 17658
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_3.fasta
## 16512
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_4.fasta
## 17030
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_5.fasta
## 16614
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_6.fasta
## 16320
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_7.fasta
## 16174
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_8.fasta
## 16192
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_9.fasta
## 16528
## 16S_v04_HmmCut.fasta
## 13224
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 2808
table(data$Subject)
##
## 12s_v010_final.fasta
## 16948
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_1.fasta
## 15894
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 15530
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_2.fasta
## 15780
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 15862
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_4.fasta
## 15700
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_5.fasta
## 15908
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 15324
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_7.fasta
## 15434
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_8.fasta
## 16196
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 16038
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_1.fasta
## 16468
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_10.fasta
## 16072
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 16080
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_3.fasta
## 16470
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_4.fasta
## 16154
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 16126
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_6.fasta
## 16024
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_7.fasta
## 16296
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_8.fasta
## 16062
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_9.fasta
## 16268
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_1.fasta
## 14966
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_10.fasta
## 14854
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_2.fasta
## 15352
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_3.fasta
## 15118
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_4.fasta
## 15274
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_5.fasta
## 15256
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_6.fasta
## 14744
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_7.fasta
## 15020
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_8.fasta
## 14828
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_9.fasta
## 15274
## 12S_v10_HmmCut.fasta
## 11732
## 16S_v04_final.fasta
## 19470
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_1.fasta
## 17626
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 16826
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_2.fasta
## 17332
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 17298
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_4.fasta
## 17600
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_5.fasta
## 17770
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 16762
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_7.fasta
## 17730
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_8.fasta
## 16610
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 17000
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_1.fasta
## 18248
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_10.fasta
## 18446
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 18110
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_3.fasta
## 17614
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_4.fasta
## 18126
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 18740
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_6.fasta
## 17816
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_7.fasta
## 18572
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_8.fasta
## 18464
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_9.fasta
## 18744
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_1.fasta
## 17498
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_10.fasta
## 16792
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_2.fasta
## 17658
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_3.fasta
## 16512
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_4.fasta
## 17030
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_5.fasta
## 16614
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_6.fasta
## 16320
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_7.fasta
## 16174
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_8.fasta
## 16192
## 16S_v04_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_9.fasta
## 16528
## 16S_v04_HmmCut.fasta
## 13224
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 2808
## c01_v03_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 2808
twelveS_data <- data |> filter(Subject == '12s_v010_final.fasta')
sixteenS_data <- data |> filter(Subject == '16S_v04_final.fasta')
table(twelveS_data$Query)
##
## KWest_16S_PooledTrue.fa
## 3712
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa
## 1946
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_noLulu_RESULTS_dada2_asv.fa
## 1946
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_Lulu_RESULTS_dada2_asv.fa
## 1308
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_noLulu_RESULTS_dada2_asv.fa
## 1308
## make_12s_16s_simulated_reads_6-fakeGenes_GreenGenes_RESULTS_dada2_asv.fa
## 1188
## make_12s_16s_simulated_reads_6-fakeGenes_Random_RESULTS_dada2_asv.fa
## 1200
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_12S_RESULTS_dada2_asv.fa
## 472
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_16S_RESULTS_dada2_asv.fa
## 386
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_12S_RESULTS_dada2_asv.fa
## 1990
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_16S_RESULTS_dada2_asv.fa
## 1492
table(sixteenS_data$Query)
##
## KWest_16S_PooledTrue.fa
## 5750
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa
## 1488
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_noLulu_RESULTS_dada2_asv.fa
## 1488
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_Lulu_RESULTS_dada2_asv.fa
## 1888
## make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_noLulu_RESULTS_dada2_asv.fa
## 1888
## make_12s_16s_simulated_reads_6-fakeGenes_GreenGenes_RESULTS_dada2_asv.fa
## 1196
## make_12s_16s_simulated_reads_6-fakeGenes_Random_RESULTS_dada2_asv.fa
## 1204
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_12S_RESULTS_dada2_asv.fa
## 374
## make_12s_16s_simulated_reads_7-Lutjanids_Mock_runEDNAFlow_16S_RESULTS_dada2_asv.fa
## 488
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_12S_RESULTS_dada2_asv.fa
## 1548
## make_12s_16s_simulated_reads_8-Rottnest_runEDNAFLOW_16S_RESULTS_dada2_asv.fa
## 2158
table(sixteenS_data$Subject)
##
## 16S_v04_final.fasta
## 19470
twelveS_data_vs_12S_100 <- twelveS_data |> filter(Query == 'make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa')
sixteenS_data_vs_16S_100 <- sixteenS_data |> filter(Query == 'make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_Lulu_RESULTS_dada2_asv.fa' )
twelveS_data_vs_12S_100 |> select(Type, species) |> filter(species != 'dropped' &
!is.na(species)) |>
group_by(Type) |> count(species) |> summarise(n = n()) |>
ggplot(aes(x = Type, y = n, fill = n)) + geom_col() + coord_flip() +
theme_minimal() +
ylab('Count') +
ggtitle('12S: Species-level hits per classifier')
twelveS_data_vs_12S_100 |> select(Type, genus) |> filter(genus != 'dropped' &
!is.na(genus)) |>
group_by(Type) |> count(genus) |> summarise(n = n()) |>
ggplot(aes(x = Type, y = n, fill = n)) + geom_col() + coord_flip() +
theme_minimal() +
ylab('Count') +
ggtitle('12S: Genus-level hits per classifier')
twelveS_truth <- truth |> filter(Query == 'make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa') |> select(OTU, family, species) |> rename(True_OTU = OTU, True_family = family, True_species = species)
head(twelveS_truth)
## # A tibble: 6 × 3
## True_OTU True_family True_species
## <chr> <chr> <chr>
## 1 ASV_1 Syngnathidae Phyllopteryx taeniolatus
## 2 ASV_2 Carcharhinidae Glyphis garricki
## 3 ASV_3 Mullidae Parupeneus barberinus
## 4 ASV_4 Holocentridae Myripristis vittata
## 5 ASV_5 Scincidae Tropidophorus hainanus
## 6 ASV_6 Anatidae Aythya nyroca
twelveS_data_vs_12S_100 |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
mutate(Correct = True_species == species) |>
filter(species != 'dropped' & !is.na(species)) |>
group_by(Type) |> count(Correct) |>
ggplot(aes(x = fct_rev(fct_reorder2(Type, Correct, n)), fill = Correct, y = n))+ geom_col() +
coord_flip() + theme_minimal() + xlab('Type') +
ggtitle('12S: Correct and incorrect species-level classifications (absolute)') +
scale_fill_manual(values = c("#E69F00", "#56B4E9", "#009E73",
"#F0E442", "#0072B2", "#D55E00", "#CC79A7"))
cols <- c('Correct species' = "#009E73", 'Correct genus'="#56B4E9", 'Correct family' = "#0072B2", 'Incorrect family' = "#E69F00", 'Incorrect genus'="#F0E442", 'Incorrect species'="#D55E00", 'NoHit'= "#CC79A7")
twelve_s_relative_plot <- twelveS_data_vs_12S_100 |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
separate(True_species, into = c('True_Genus', 'True_Epiteth'), remove = FALSE)|>
mutate(species = na_if(species, 'dropped')) |>
mutate(genus = na_if(genus, 'dropped')) |>
mutate(CorrectSpecies = case_when(!is.na(species) & True_species == species ~ 'Correct species',
!is.na(species) & True_species != species ~ 'Incorrect species',
!is.na(genus) & !is.na(True_Genus) & True_Genus == genus ~ 'Correct genus',
!is.na(genus) & !is.na(True_Genus) & True_Genus != genus ~ 'Incorrect genus',
!is.na(family) & True_family == family ~ 'Correct family',
!is.na(family) & True_family != family ~ 'Incorrect family',
TRUE ~ NA)) |>
group_by(Type) |>
count(CorrectSpecies) |>
mutate(total = sum(n)) |>
mutate(missing = 99 - total) |>
group_modify(~ add_row(.x)) |>
group_modify(~ {
.x |> mutate(new_col= max(missing, na.rm=TRUE)) |>
mutate(n = case_when(is.na(CorrectSpecies) & is.na(missing) ~ new_col,
TRUE ~ n)) |>
select(-new_col)
} ) |>
mutate(total = 99) |>
mutate(perc = n / total * 100) |>
mutate(CorrectSpecies = replace_na(CorrectSpecies, 'NoHit')) |>
mutate(CorrectSpecies = factor(CorrectSpecies, rev(c('Correct species', 'Correct genus', 'Correct family', 'Incorrect family', 'Incorrect genus', 'Incorrect species', 'NoHit')))) |>
ggplot(aes(x = fct_rev(fct_reorder2(Type, CorrectSpecies, n)), fill = CorrectSpecies, y = perc))+
geom_col() +
coord_flip() +
theme_minimal() +
ylab('Percentage') + xlab('Type') +
ggtitle('12S: Correct and incorrect species-level classifications (relative)') +
scale_fill_manual(name = 'Outcome', values = cols, breaks=names(cols))
twelve_s_relative_plot
## Calculate Upset-based species sightings
type_list <- twelveS_data_vs_12S_100 |> select(Type, species) |> unique() |> filter(!is.na(species) & species != 'dropped') |>
group_by(species) |>
summarize('Type' = list(Type))
a <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('12S: Shared species') +
ylab('Species')
a
## Warning: Removed 56 rows containing non-finite values (`stat_count()`).
type_list <- twelveS_data_vs_12S_100 |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
filter(species == True_species) |>
filter(species != 'dropped' & !is.na(species)) |>
select(Type, species) |> unique() |>
group_by(species) |>
summarize('Type' = list(Type))
b <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('12S: Shared correct species') +
ylab('Species')
b
## Warning: Removed 27 rows containing non-finite values (`stat_count()`).
type_list <- twelveS_data_vs_12S_100 |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
filter(species != True_species) |>
filter(species != 'dropped' & !is.na(species)) |>
select(Type, species) |> unique() |>
group_by(species) |>
summarize('Type' = list(Type))
c <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('12S: Shared incorrect species') +
ylab('Species')
c
## Warning: Removed 13 rows containing non-finite values (`stat_count()`).
a + b + c & ylim(c(0, 30)) &
theme(
# Hide panel borders and remove grid lines
panel.border = element_blank(),
panel.grid.major = element_blank(),
panel.background = element_blank(),
panel.grid.minor = element_blank(),
#panel.grid.major.y = element_line(),
# Change axis line
axis.line = element_line(colour = "black")
)
add_scores <- function(twelveS_data_vs_12S_100_with_MaxTruth, twelveS_truth ) {
twelveS_data_vs_12S_100_with_MaxTruth|> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
separate(True_species, into = c('True_Genus', 'True_Epiteth'), remove = FALSE)|>
mutate(species = na_if(species, 'dropped')) |>
mutate(genus = na_if(genus, 'dropped')) |>
mutate(CorrectSpecies = case_when(!is.na(species) & True_species == species ~ 'Correct species',
!is.na(species) & True_species != species ~ 'Incorrect species',
!is.na(genus) & !is.na(True_Genus) & True_Genus == genus ~ 'Correct genus',
!is.na(genus) & !is.na(True_Genus) & True_Genus != genus ~ 'Incorrect genus',
!is.na(family) & True_family == family ~ 'Correct family',
!is.na(family) & True_family != family ~ 'Incorrect family',
TRUE ~ NA)) |>
group_by(Type) |>
summarise(TP = sum(str_detect(CorrectSpecies, pattern='Correct species'), na.rm=TRUE),
FP = sum(str_detect(CorrectSpecies, pattern = 'Incorrect species'), na.rm=TRUE),
TN = sum(str_detect(replace_na(CorrectSpecies,'NA'), pattern='NA') & is.na(True_species), na.rm=TRUE),
FN = sum(is.na(species) & !is.na(True_species))) |>
mutate(sums = TP + FP + TN + FN) |>
mutate(missing = 99 - sums) |>
mutate(FN = FN + missing) |>
mutate(sums = TP + FP + TN + FN) |>
select(-c(missing, sums))
}
scores <- add_scores(twelveS_data_vs_12S_100, twelveS_truth)
precision <- function(TP, FP) {
TP / (TP + FP )
}
recall <- function(TP, FN) {
TP / (TP + FN)
}
f1 <- function(precision, recall) {
2*precision * recall / (precision + recall)
}
f0.5 <- function(precision, recall) {
((1 + 0.5^2) * precision * recall) / (0.5^2 * precision + recall)
}
accuracy <- function(TP, FP, FN, TN) {
(TN + TP) / (TN + TP + FP + FN)
}
scores <- scores |> rowwise() |> mutate(recall = recall(TP, FN), precision = precision(TP, FP),
f1 = f1(precision, recall), f0.5 = f0.5(precision, recall), accuracy = accuracy(TP, FP, FN, TN))
scores
## # A tibble: 11 × 10
## # Rowwise:
## Type TP FP TN FN recall precision f1 f0.5 accuracy
## <chr> <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 BLAST100 118 12 0 -31 1.36 0.908 1.09 0.972 1.19
## 2 BLAST97 96 16 0 -13 1.16 0.857 0.985 0.904 0.970
## 3 Kraken_0.0 108 28 0 -37 1.52 0.794 1.04 0.878 1.09
## 4 Kraken_0.1 94 10 0 -5 1.06 0.904 0.974 0.931 0.949
## 5 Kraken_0.2 72 6 0 21 0.774 0.923 0.842 0.889 0.727
## 6 MMSeqs2 118 26 0 -45 1.62 0.819 1.09 0.909 1.19
## 7 Metabuli 54 12 0 33 0.621 0.818 0.706 0.769 0.545
## 8 Mothur 82 40 0 -23 1.39 0.672 0.906 0.750 0.828
## 9 NBC 84 38 0 -23 1.38 0.689 0.918 0.765 0.848
## 10 Qiime2 62 92 0 -55 8.86 0.403 0.770 0.498 0.626
## 11 VSEARCH 80 30 0 -11 1.16 0.727 0.894 0.786 0.808
twelveS_scoreS_plot <- scores |> select(-c(TP, FP, FN, TN)) |> pivot_longer(-Type, names_to='Score') |> ggplot(aes(x = fct_rev(fct_reorder(Type, value)), y = value, group=Score, color = Score, fill =Score)) + geom_line() + ylim(c(0, 1)) + theme_minimal_hgrid()+ theme(axis.text.x = element_text( angle = 45, hjust = 1)) + ylab('Score') + xlab('Tool') + ggtitle('12S scores')
twelveS_scoreS_plot
## Warning: Removed 13 rows containing missing values (`geom_line()`).
Let’s also make a heatmap from that
b <- scores$Type
m <- scores |> select(-Type) |> select(accuracy, recall, precision, f1, f0.5) |> as.matrix()
rownames(m) <- b
pheatmap(m, cluster_cols=FALSE, display_numbers = TRUE,
color = colorRampPalette(brewer.pal(n = 7, name =
"RdYlGn"))(100))
b <- scores$Type
m <- scores |> select(-Type) |> select(TP, FP, FN) |> as.matrix()
rownames(m) <- b
pheatmap(m, cluster_cols=FALSE, display_numbers = TRUE,
color = colorRampPalette(brewer.pal(n = 7, name =
"RdYlGn"))(100))
table(twelveS_data_vs_12S_100$Type)
##
## BLAST100 BLAST97 Kraken_0.0 Kraken_0.1 Kraken_0.2 Metabuli MMSeqs2
## 172 190 198 198 198 132 198
## Mothur NBC Qiime2 VSEARCH
## 198 198 154 110
First, we count the per-OTU species hits
twelveS_data_vs_12S_100_maxCount <- twelveS_data_vs_12S_100 |>
mutate(species = na_if(species, 'dropped')) |>
filter(!is.na(species)) |>
#filter(! Type %in% c('Mothur', 'VSEARCH', 'Kraken_0.2', 'Qiime2', 'Metabuli', 'NBC', 'BLAST97', 'Kraken_0.0', 'Kraken_0.1')) |>
group_by(Query, Subject, OTU) |>
count(species) |>
# double check the truth
#left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
#mutate(Truth = True_species == species) |>
# pull out the per-group highest n
filter( n > 4) |>
slice_max(n, n=1, with_ties = FALSE) |>
mutate(Type = 'MaxCount', .before = 'Query') |>
select(-n)
twelveS_data_vs_12S_100_maxCount
## # A tibble: 76 × 5
## # Groups: Query, Subject, OTU [76]
## Type Query Subject OTU species
## <chr> <chr> <chr> <chr> <chr>
## 1 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_1 Phyllo…
## 2 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Cirrip…
## 3 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Sterco…
## 4 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Carcha…
## 5 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Hemigy…
## 6 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Ctenoc…
## 7 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Daptio…
## 8 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Engrau…
## 9 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Bathyr…
## 10 MaxCount make_12s_16s_simulated_reads_5-BetterDatabase… 12s_v0… ASV_… Tripho…
## # ℹ 66 more rows
twelveS_data_vs_12S_100_with_MaxTruth <- twelveS_data_vs_12S_100 |>
bind_rows(twelveS_data_vs_12S_100_maxCount) #|>
#filter(! Type %in% c('Mothur', 'VSEARCH', 'Kraken_0.2', 'Qiime2', 'Metabuli', 'NBC', 'BLAST97', 'Kraken_0.0', 'Kraken_0.1'))
maxTruth_scores <- add_scores(twelveS_data_vs_12S_100_with_MaxTruth, twelveS_truth )
maxTruth_scores <- maxTruth_scores |> rowwise() |> mutate(recall = recall(TP, FN), precision = precision(TP, FP),
f1 = f1(precision, recall), f0.5 = f0.5(precision, recall), accuracy = accuracy(TP, FP, FN, TN))
maxTruth_scoreS_plot <- maxTruth_scores |> select(-c(TP, FP, FN, TN)) |> pivot_longer(-Type, names_to='Score') |> ggplot(aes(x = fct_rev(fct_reorder(Type, value)), y = value, group=Score, color = Score, fill =Score)) + geom_line() + ylim(c(0, 1)) + theme_minimal_hgrid()+ theme(axis.text.x = element_text( angle = 45, hjust = 1)) + ylab('Score') + xlab('Tool') + geom_point() + ggtitle('12S scores')
maxTruth_scoreS_plot
## Warning: Removed 13 rows containing missing values (`geom_line()`).
## Warning: Removed 15 rows containing missing values (`geom_point()`).
Interestingly, just counting the labels is not good! It performs worse
than BLAST.
sixteenS_truth <- truth |> filter(Query == 'make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_16S_Lulu_RESULTS_dada2_asv.fa') |> select(OTU, family, species) |> rename(True_OTU = OTU, True_family = family, True_species = species)
head(sixteenS_truth)
## # A tibble: 6 × 3
## True_OTU True_family True_species
## <chr> <chr> <chr>
## 1 ASV_1 Syngnathidae Phyllopteryx taeniolatus
## 2 ASV_2 Carcharhinidae Glyphis garricki
## 3 ASV_3 Merlucciidae Merluccius productus
## 4 ASV_4 Mullidae Parupeneus barberinus
## 5 ASV_5 Syngnathidae Hippocampus algiricus
## 6 ASV_6 Eleotridae Bostrychus sinensis
sixteenS_relative_plot <- sixteenS_data_vs_16S_100 |> left_join(sixteenS_truth, by = c('OTU' = 'True_OTU')) |>
separate(True_species, into = c('True_Genus', 'True_Epiteth'), remove = FALSE)|>
mutate(species = na_if(species, 'dropped')) |>
mutate(genus = na_if(genus, 'dropped')) |>
mutate(CorrectSpecies = case_when(!is.na(species) & True_species == species ~ 'Correct species',
!is.na(species) & True_species != species ~ 'Incorrect species',
!is.na(genus) & !is.na(True_Genus) & True_Genus == genus ~ 'Correct genus',
!is.na(genus) & !is.na(True_Genus) & True_Genus != genus ~ 'Incorrect genus',
!is.na(family) & True_family == family ~ 'Correct family',
!is.na(family) & True_family != family ~ 'Incorrect family',
TRUE ~ NA)) |>
group_by(Type) |>
count(CorrectSpecies) |>
mutate(total = sum(n)) |>
mutate(missing = 99 - total) |>
group_modify(~ add_row(.x)) |>
group_modify(~ {
.x |> mutate(new_col= max(missing, na.rm=TRUE)) |>
mutate(n = case_when(is.na(CorrectSpecies) & is.na(missing) ~ new_col,
TRUE ~ n)) |>
select(-new_col)
} ) |>
mutate(total = 99) |>
mutate(perc = n / total * 100) |>
mutate(CorrectSpecies = replace_na(CorrectSpecies, 'NoHit')) |>
mutate(CorrectSpecies = factor(CorrectSpecies, rev(c('Correct species', 'Correct genus', 'Correct family', 'Incorrect family', 'Incorrect genus', 'Incorrect species', 'NoHit')))) |>
ggplot(aes(x = fct_rev(fct_reorder2(Type, CorrectSpecies, n)), fill = CorrectSpecies, y = perc))+
geom_col() +
coord_flip() +
theme_minimal() +
ylab('Percentage') + xlab('Type') +
ggtitle('16S: Correct and incorrect species-level classifications (relative)') +
scale_fill_manual(name = 'Outcome', values = cols, breaks=names(cols))
sixteenS_relative_plot
scores <- add_scores(sixteenS_data_vs_16S_100, sixteenS_truth)
scores
## # A tibble: 11 × 5
## Type TP FP TN FN
## <chr> <int> <int> <int> <dbl>
## 1 BLAST100 102 0 0 -3
## 2 BLAST97 96 10 0 -7
## 3 Kraken_0.0 104 30 0 -35
## 4 Kraken_0.1 90 20 0 -11
## 5 Kraken_0.2 70 12 0 17
## 6 MMSeqs2 120 10 0 -31
## 7 Metabuli 32 6 0 61
## 8 Mothur 100 28 0 -29
## 9 NBC 108 24 0 -33
## 10 Qiime2 90 68 0 -59
## 11 VSEARCH 86 24 0 -11
scores <- scores |> rowwise() |> mutate(recall = recall(TP, FN), precision = precision(TP, FP),
f1 = f1(precision, recall), f0.5 = f0.5(precision, recall), accuracy = accuracy(TP, FP, FN, TN))
scores
## # A tibble: 11 × 10
## # Rowwise:
## Type TP FP TN FN recall precision f1 f0.5 accuracy
## <chr> <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 BLAST100 102 0 0 -3 1.03 1 1.01 1.01 1.03
## 2 BLAST97 96 10 0 -7 1.08 0.906 0.985 0.936 0.970
## 3 Kraken_0.0 104 30 0 -35 1.51 0.776 1.02 0.860 1.05
## 4 Kraken_0.1 90 20 0 -11 1.14 0.818 0.952 0.867 0.909
## 5 Kraken_0.2 70 12 0 17 0.805 0.854 0.828 0.843 0.707
## 6 MMSeqs2 120 10 0 -31 1.35 0.923 1.10 0.985 1.21
## 7 Metabuli 32 6 0 61 0.344 0.842 0.489 0.653 0.323
## 8 Mothur 100 28 0 -29 1.41 0.781 1.01 0.858 1.01
## 9 NBC 108 24 0 -33 1.44 0.818 1.04 0.896 1.09
## 10 Qiime2 90 68 0 -59 2.90 0.570 0.952 0.679 0.909
## 11 VSEARCH 86 24 0 -11 1.15 0.782 0.930 0.835 0.869
sixteenS_score_plot <- scores |> select(-c(TP, FP, FN, TN)) |> pivot_longer(-Type, names_to='Score') |> ggplot(aes(x = fct_rev(fct_reorder(Type, value)), y = value, group=Score, color = Score, fill =Score)) + geom_line() + ylim(c(0, 1)) + theme_minimal_hgrid() + theme(axis.text.x = element_text( angle = 45, hjust = 1)) + ylab('Score') + xlab('Tool') + ggtitle('16S scores')
sixteenS_score_plot
## Warning: Removed 19 rows containing missing values (`geom_line()`).
b <- scores$Type
m <- scores |> select(-Type) |> select(accuracy, recall, precision, f1, f0.5) |> as.matrix()
rownames(m) <- b
pheatmap(m, cluster_cols=FALSE, display_numbers = TRUE,
color = colorRampPalette(brewer.pal(n = 7, name =
"RdYlGn"))(100))
b <- scores$Type
m <- scores |> select(-Type) |> select(TP, FP, FN) |> as.matrix()
rownames(m) <- b
pheatmap(m, cluster_cols=FALSE, display_numbers = TRUE,
color = colorRampPalette(brewer.pal(n = 7, name =
"RdYlGn"))(100))
## Calculate Upset-based species sightings
type_list <- sixteenS_data_vs_16S_100 |> select(Type, species) |> unique() |> filter(!is.na(species) & species != 'dropped') |>
group_by(species) |>
summarize('Type' = list(Type))
a <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('16S: Shared species') +
ylab('Species')
a
## Warning: Removed 47 rows containing non-finite values (`stat_count()`).
type_list <- sixteenS_data_vs_16S_100 |> left_join(sixteenS_truth, by = c('OTU' = 'True_OTU')) |>
filter(species == True_species) |>
filter(species != 'dropped' & !is.na(species)) |>
select(Type, species) |> unique() |>
group_by(species) |>
summarize('Type' = list(Type))
b <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('16S: Shared correct species') +
ylab('Species')
b
## Warning: Removed 25 rows containing non-finite values (`stat_count()`).
type_list <- sixteenS_data_vs_16S_100 |> left_join(sixteenS_truth, by = c('OTU' = 'True_OTU')) |>
filter(species != True_species) |>
filter(species != 'dropped' & !is.na(species)) |>
select(Type, species) |> unique() |>
group_by(species) |>
summarize('Type' = list(Type))
c <- type_list |>
ggplot(aes(x = Type)) +
geom_bar() +
scale_x_upset(n_intersections = 12) +
ggtitle('16S: Shared incorrect species') +
ylab('Species')
c
## Warning: Removed 8 rows containing non-finite values (`stat_count()`).
a + b + c & ylim(c(0, 20)) &
theme(
# Hide panel borders and remove grid lines
panel.border = element_blank(),
panel.grid.major = element_blank(),
panel.background = element_blank(),
panel.grid.minor = element_blank(),
#panel.grid.major.y = element_line(),
# Change axis line
axis.line = element_line(colour = "black")
)
sixteenS_relative_plot / twelve_s_relative_plot
(sixteenS_score_plot +geom_point() + theme(axis.title.x = element_blank()))/ (twelveS_scoreS_plot + geom_point())
## Warning: Removed 19 rows containing missing values (`geom_line()`).
## Warning: Removed 20 rows containing missing values (`geom_point()`).
## Warning: Removed 13 rows containing missing values (`geom_line()`).
## Warning: Removed 15 rows containing missing values (`geom_point()`).
twelve_exclusions <- data |> filter(str_starts(Subject, '12s_v010_final.fasta_Taxonomies.CountedFams.txt_')) |>
filter(Query == 'make_12s_16s_simulated_reads_5-BetterDatabaseARTSimulation_runEDNAFLOW_12S_Lulu_RESULTS_dada2_asv.fa')
table(twelve_exclusions$Subject)
##
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_1.fasta
## 1674
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_10.fasta
## 1616
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_2.fasta
## 1644
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_3.fasta
## 1676
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_4.fasta
## 1652
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_5.fasta
## 1690
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_6.fasta
## 1572
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_7.fasta
## 1526
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_8.fasta
## 1704
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_fifty_subset_9.fasta
## 1682
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_1.fasta
## 1814
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_10.fasta
## 1780
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_2.fasta
## 1728
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_3.fasta
## 1846
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_4.fasta
## 1712
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_5.fasta
## 1726
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_6.fasta
## 1712
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_7.fasta
## 1788
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_8.fasta
## 1770
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_seventy_subset_9.fasta
## 1782
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_1.fasta
## 1474
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_10.fasta
## 1466
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_2.fasta
## 1564
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_3.fasta
## 1526
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_4.fasta
## 1476
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_5.fasta
## 1514
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_6.fasta
## 1494
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_7.fasta
## 1458
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_8.fasta
## 1500
## 12s_v010_final.fasta_Taxonomies.CountedFams.txt_thirty_subset_9.fasta
## 1516
twelve_exclusions_split <- twelve_exclusions |> separate(Subject, into = c('before', 'hit'), sep='.txt_') |>
# get rid of leftover non-subsetted databases
filter(!is.na(hit)) |>
separate(hit, into=c('Database', 'after'), sep='_subset')
twelve_exclusions_split_averaged <- twelve_exclusions_split |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
separate(True_species, into = c('True_Genus', 'True_Epiteth'), remove = FALSE)|>
mutate(species = na_if(species, 'dropped')) |>
mutate(genus = na_if(genus, 'dropped')) |>
mutate(CorrectSpecies = case_when(!is.na(species) & True_species == species ~ 'Correct species',
!is.na(species) & True_species != species ~ 'Incorrect species',
!is.na(genus) & !is.na(True_Genus) & True_Genus == genus ~ 'Correct genus',
!is.na(genus) & !is.na(True_Genus) & True_Genus != genus ~ 'Incorrect genus',
!is.na(family) & True_family == family ~ 'Correct family',
!is.na(family) & True_family != family ~ 'Incorrect family',
TRUE ~ NA)) |>
group_by(Type, Database, after) |>
summarise(TP = sum(str_detect(CorrectSpecies, pattern='Correct species'), na.rm=TRUE),
FP = sum(str_detect(CorrectSpecies, pattern = 'Incorrect species'), na.rm=TRUE),
TN = sum(str_detect(replace_na(CorrectSpecies,'NA'), pattern='NA') & is.na(True_species), na.rm=TRUE),
FN = sum(is.na(species) & !is.na(True_species))) |>
mutate(sums = TP + FP + TN + FN) |>
mutate(missing = 99 - sums) |>
mutate(FN = FN + missing) |>
mutate(sums = TP + FP + TN + FN) |>
select(-c(missing, sums)) |>
group_by(Type, Database) |>
summarise(mean_TP = mean(TP),
mean_FP = mean(FP),
mean_TN = mean(TN),
mean_FN = mean(FN)) |>
rowwise() |>
mutate(recall = recall(mean_TP, mean_FN),
precision = precision(mean_TP, mean_FP),
f1 = f1(precision, recall),
f0.5 = f0.5(precision, recall),
accuracy = accuracy(mean_TP, mean_FP, mean_FN, mean_TN))
## `summarise()` has grouped output by 'Type', 'Database'. You can override using
## the `.groups` argument.
## `summarise()` has grouped output by 'Type'. You can override using the
## `.groups` argument.
twelve_exclusions_split_averaged <- twelve_exclusions_split_averaged |>
mutate(Database = case_when ( Database == 'fifty' ~ '50%',
Database == 'seventy' ~ '70%',
Database == 'thirty' ~ '30%',
TRUE ~ Database))
f1_pl <- twelve_exclusions_split_averaged |>
ggplot(aes(x = Type, y = f1, group = Database, color = Database, fill = Database)) +
geom_point() +
geom_line() +
theme_minimal()
f0.5_pl <- twelve_exclusions_split_averaged |>
ggplot(aes(x = Type, y = f0.5, group = Database, color = Database, fill = Database)) +
geom_point() +
geom_line() +
theme_minimal()
precision_pl <- twelve_exclusions_split_averaged |>
ggplot(aes(x = Type, y = precision, group = Database, color = Database, fill = Database)) +
geom_point() +
geom_line() +
theme_minimal()
recall_pl <- twelve_exclusions_split_averaged |>
ggplot(aes(x = Type, y = recall, group = Database, color = Database, fill = Database)) +
geom_point() +
geom_line() +
theme_minimal()
(f1_pl / f0.5_pl / precision_pl / recall_pl) + plot_layout(guides = 'collect')
Lets zero in on the precision and make boxplots with jitter dots
un_summarised_twelve <- twelve_exclusions_split |> left_join(twelveS_truth, by = c('OTU' = 'True_OTU')) |>
separate(True_species, into = c('True_Genus', 'True_Epiteth'), remove = FALSE)|>
mutate(species = na_if(species, 'dropped')) |>
mutate(genus = na_if(genus, 'dropped')) |>
mutate(CorrectSpecies = case_when(!is.na(species) & True_species == species ~ 'Correct species',
!is.na(species) & True_species != species ~ 'Incorrect species',
!is.na(genus) & !is.na(True_Genus) & True_Genus == genus ~ 'Correct genus',
!is.na(genus) & !is.na(True_Genus) & True_Genus != genus ~ 'Incorrect genus',
!is.na(family) & True_family == family ~ 'Correct family',
!is.na(family) & True_family != family ~ 'Incorrect family',
TRUE ~ NA)) |>
group_by(Type, Database, after) |>
summarise(TP = sum(str_detect(CorrectSpecies, pattern='Correct species'), na.rm=TRUE),
FP = sum(str_detect(CorrectSpecies, pattern = 'Incorrect species'), na.rm=TRUE),
TN = sum(str_detect(replace_na(CorrectSpecies,'NA'), pattern='NA') & is.na(True_species), na.rm=TRUE),
FN = sum(is.na(species) & !is.na(True_species))) |>
mutate(sums = TP + FP + TN + FN) |>
mutate(missing = 99 - sums) |>
mutate(FN = FN + missing) |>
mutate(sums = TP + FP + TN + FN) |>
select(-c(missing, sums)) |>
rowwise() |>
mutate(recall = recall(TP, FN),
precision = precision(TP, FP),
f1 = f1(precision, recall),
f0.5 = f0.5(precision, recall),
accuracy = accuracy(TP, FP, FN, TN)) |>
mutate(Database = case_when ( Database == 'fifty' ~ '50%',
Database == 'seventy' ~ '70%',
Database == 'thirty' ~ '30%',
TRUE ~ Database))
## `summarise()` has grouped output by 'Type', 'Database'. You can override using
## the `.groups` argument.
un_summarised_twelve |> group_by(Type, Database) |> mutate(best = max(mean(precision))) |>
ggplot(aes(x = fct_reorder(Type, best), group = interaction(Type, Database), color=Database, y = precision)) +
geom_boxplot(outlier.shape = NA) +
coord_flip() +
theme_minimal() +
xlab('Type') +
ylab('Precision') +
geom_point(position = position_jitterdodge(), alpha=0.5)
un_summarised_twelve |> group_by(Type, Database) |> mutate(best = max(mean(f0.5))) |>
ggplot(aes(x = fct_reorder(Type, best), group = interaction(Type, Database), color=Database, y = f0.5)) +
geom_boxplot(outlier.shape = NA) +
coord_flip() +
theme_minimal() +
xlab('Type') +
ylab('f0.5') +
ylim(c(0, 1)) +
geom_point(position = position_jitterdodge(), alpha=0.5)
un_summarised_twelve |> group_by(Type, Database) |> mutate(best = max(mean(recall))) |>
ggplot(aes(x = fct_reorder(Type, best), group = interaction(Type, Database), color=Database, y = recall)) +
geom_boxplot(outlier.shape = NA) +
coord_flip() +
theme_minimal() +
xlab('Type') +
ylab('f0.5') +
ylim(c(0, 1)) +
geom_point(position = position_jitterdodge(), alpha=0.5)
## Warning: Removed 51 rows containing non-finite values (`stat_boxplot()`).
## Warning: Removed 51 rows containing missing values (`geom_point()`).
un_summarised_twelve |>
filter(Type %in% c('BLAST100', 'Kraken_0.0', 'Qiime2')) |>
ggplot(aes(x=Database, y = precision, fill=Type)) + #fill=factor(Database, levels=c('30%','50%','70%')))) +
geom_boxplot() +
labs(fill='Type') +
ylab('Precision') +
theme_minimal()
false_positives <- un_summarised_twelve |>
filter(Type %in% c('BLAST100', 'Kraken_0.0', 'Kraken_0.1', 'MMSeqs2')) |>
ggplot(aes(x=Database, y = FP/99*100, fill=Type)) + #fill=factor(Database, levels=c('30%','50%','70%')))) +
geom_boxplot(outlier.shape=NA) +
labs(fill='Type') +
ylab('False positives (%)') +
geom_point(aes(color=Type),
position = position_jitterdodge(jitter.width = 0.2),
alpha=0.5,
show.legend = FALSE)+
theme_minimal()
false_positives
true_positives <- un_summarised_twelve |>
filter(Type %in% c('BLAST100', 'Kraken_0.0', 'Kraken_0.1', 'MMSeqs2')) |>
ggplot(aes(x=Database, y = TP/99*100, fill=Type)) + #fill=factor(Database, levels=c('30%','50%','70%')))) +
geom_boxplot(outlier.shape=NA) +
labs(fill='Type') +
ylab('True positives (%)') +
geom_point(aes(color=Type),
position = position_jitterdodge(jitter.width = 0.2),
alpha=0.5,
show.legend = FALSE)+
theme_minimal()
true_positives
false_positives/ true_positives + plot_layout(guides = 'collect') & coord_flip()
## Phylogenetic diversity
We can also easily calculate alpha diversity across these tools, as alpha diversity is the number of species. We treat classifiers/Types as sites.
Need to transform our species sightings into a table where species are columns, Types are rows, and cells are ‘counts’ (1/0)
spec_summarised <- twelve_exclusions_split |>
group_by(Type, Query, Database, after) |>
mutate(Database = case_when ( Database == 'fifty' ~ '50%',
Database == 'seventy' ~ '70%',
Database == 'thirty' ~ '30%',
TRUE ~ Database)) |>
filter(!is.na(species)) |>
summarise(`Alpha diversity index` = length(unique(species)))
## `summarise()` has grouped output by 'Type', 'Query', 'Database'. You can
## override using the `.groups` argument.
spec_summarised |>
ggplot(aes(x = Type, y = `Alpha diversity index`, fill=Type, group = Type )) +
geom_boxplot() +
geom_point(aes(color=Type),
position = position_jitterdodge(jitter.width = 0.2),
alpha=0.5,
show.legend = FALSE) +
facet_wrap(~Database) + coord_flip() + theme_minimal()
Let’s also do not all of the classifiers
spec_summarised |>
filter(Type %in% c('BLAST100', 'Kraken_0.0', 'Kraken_0.1','MMSeqs2', 'Qiime2')) |>
ggplot(aes(x = Type, y = `Alpha diversity index`, fill=Type, group = Type )) +
geom_boxplot() +
geom_point(aes(color=Type),
position = position_jitterdodge(jitter.width = 0.2),
alpha=0.5,
show.legend = FALSE) +
facet_wrap(~Database) + coord_flip() + theme_minimal()
a <- spec_summarised |>
filter(Type %in% c('BLAST100', 'BLAST97', 'Kraken_0.0', 'Kraken_0.1','MMSeqs2', 'Qiime2')) |>
group_by(Database) |>
arrange(Database) |>
group_map(~aov(`Alpha diversity index` ~ Type, data=.))
names(a) <- spec_summarised |> arrange(Database) |> pull(Database) |> unique() # I don't like this :(
a
## $`30%`
## Call:
## aov(formula = `Alpha diversity index` ~ Type, data = .)
##
## Terms:
## Type Residuals
## Sum of Squares 7244.6 707.0
## Deg. of Freedom 5 54
##
## Residual standard error: 3.618369
## Estimated effects may be unbalanced
##
## $`50%`
## Call:
## aov(formula = `Alpha diversity index` ~ Type, data = .)
##
## Terms:
## Type Residuals
## Sum of Squares 4749.0 1519.6
## Deg. of Freedom 5 54
##
## Residual standard error: 5.304785
## Estimated effects may be unbalanced
##
## $`70%`
## Call:
## aov(formula = `Alpha diversity index` ~ Type, data = .)
##
## Terms:
## Type Residuals
## Sum of Squares 4510.2 1509.4
## Deg. of Freedom 5 54
##
## Residual standard error: 5.286951
## Estimated effects may be unbalanced
library(agricolae)
## Registered S3 methods overwritten by 'klaR':
## method from
## predict.rda vegan
## print.rda vegan
## plot.rda vegan
groupslist <- list()
for(key in names(a)) {
print(key)
groupslist[[key]] <- HSD.test(a[[key]], 'Type')$groups|>
as_tibble(rownames = 'Type') |>
select(-`Alpha diversity index`)
}
## [1] "30%"
## [1] "50%"
## [1] "70%"
groups_df <- bind_rows(groupslist, .id='Database')
spec_summarised |>
filter(Type %in% c('BLAST100', 'BLAST97', 'Kraken_0.0', 'Kraken_0.1','MMSeqs2', 'Qiime2')) |>
left_join(groups_df, by = c('Database', 'Type')) |>
ggplot(aes(x = Type, y = `Alpha diversity index`, fill=Type, group = Type )) +
geom_boxplot(outlier.shape=NA) +
geom_point(aes(color=Type),
position = position_jitterdodge(jitter.width = 0.2),
alpha=0.5,
show.legend = FALSE) +
facet_wrap(~Database) +
geom_text(aes(x = Type, y = max(`Alpha diversity index`) + 2, label = groups),
#col = 'black',
size = 4) +
#coord_flip() +
theme_minimal() +
theme(axis.text.x = element_text( angle = 90, hjust = 1)) +
guides(fill="none")